English | 简体中文
Version: 1.0.0
Category: Image Classification
Algorithm: MobileNetV2 0.35 Rep
Dataset: VWW
Class: Not a person, Person
The model is a vision model designed for person classification. It utilizes the SSCMA training and employs the MobileNetV2 (0.35) Rep algorithm.
| Type | Batch | Shape | Remark | |
|---|---|---|---|---|
| Input | image | 1 | [64, 64, 3] | The input image should be resized to 64x64 pixels |
| Output | classification | 1 | [2] | The output is a 2-element vector, which represents the probability of the input image belonging to each class |
| Backend | Precision | Top-1(%) | Flops(MB) | Params(M) | Inference(ms) | Download | Author |
|---|---|---|---|---|---|---|---|
| PyTorch | FLOAT32 | 85.22 | 34 | 2.71 | - | Link | Seeed Studio |
| ONNX | FLOAT32 | 85.23 | - | 2.71 | - | Link | Seeed Studio |
| TFLite | FLOAT32 | 85.23 | - | 2.71 | - | Link | Seeed Studio |
| TFLite | INT8 | 85.26 | - | 2.71 | 286(1) | Link | Seeed Studio |
| TFLite(vela) | INT8 | 85.26 | - | 2.71 | 8.0(2) | Link | Seeed Studio |
Table Notes:
- Backend: The deep learning framework used to infer the model.
- Precision: The numerical precision used for training the model.
- Metrics: The metrics used to evaluate the model.
- Inference(ms): The inference time of the model in milliseconds.
- 1: xiao_esp32s3.
- 2: grove_vision_ai_we2.
- Link: The link to the model.
- Author: The author of the model.
MIT